© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 28499
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to average values or averages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useState
    -0.72
     Musk
    -0.72
     DialogInterface
    -0.72
    ̀n
    -0.71
     Betis
    -0.70
     Ruk
    -0.68
    selaer
    -0.68
     kasarigan
    -0.65
    ⓧ
    -0.65
    splan
    -0.64
    POSITIVE LOGITS
     оригіналу
    0.81
    पन
    0.76
    BufferException
    0.70
     arşivlendi
    0.69
    eradish
    0.69
    }}">
    0.67
     matrimon
    0.64
     Sándor
    0.64
     Hage
    0.63
    ætter
    0.63
    Activations Density 0.029%

    No Known Activations